Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN

Zhang, Lvmin; Lin, Xin

doi:10.48550/arxiv.1706.03319

Cited by 11 publications

(18 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[11] is applied on numerous tasks such as sketch to photo, image colorization, and aerial photo to map. Similarly, [28] use a conditional GAN with Residual UNet [22] framework supplemented with embeddings from VGG19 [24] for sketch colorization task. Both show that conditional GAN and UNet are effective when paired data are readily available or can be generated.…”

Section: Domain Transfer Through Generative Adversarial Networkmentioning

confidence: 99%

“…For image translation task, some details and spatial information may be lost in the down-sampling process. UNet [22] is commonly used in image translation tasks [11,28] where details of the input image can be preserved in the output through the skip connection. We adapt such structure and our encoder mirrors the PGGAN generator structure -growing as the generator grows to a higher resolution.…”

Section: Architecturementioning

confidence: 99%

“…It utilizes a trained object detection network such as VGG19 [24] for feature extraction. As a result, style transfer gives less satisfactory results when the target domain contains object representations not seen by the pretrained object detection network [28]. Furthermore, due to the content loss being defined as the L2 difference in convolutional layers of object detection network, Style Transfer based methods fails to fundamentally change the object layout when applied to domain transfer and often relies on the objects in the content and style images having similar spacial proportions in the first place.…”

Section: Introductionmentioning

confidence: 99%

“…On the other hand, GAN has shown more promising results when provided paired data belonging to the two domains of interest. Previous works such as [11] and [28] all show promising results when paired datasets are available or can be generated. However such datasets are often expensive to obtain.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Twin-GAN -- Unpaired Cross-Domain Image Translation with Weight-Sharing GANs

2018

Preprint

View full text Add to dashboard Cite

We present a framework for translating unlabeled images from one domain into analog images in another domain. We employ a progressively growing skipconnected encoder-generator structure and train it with a GAN loss for realistic output, a cycle consistency loss for maintaining same-domain translation identity, and a semantic consistency loss that encourages the network to keep the input semantic features in the output. We apply our framework on the task of translating face images, and show that it is capable of learning semantic mappings for face images with no supervised one-to-one image mapping.

show abstract

Section: Domain Transfer Through Generative Adversarial Networkmentioning

confidence: 99%

Section: Architecturementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Twin-GAN -- Unpaired Cross-Domain Image Translation with Weight-Sharing GANs

2018

Preprint

View full text Add to dashboard Cite

show abstract

“…Specifically, a network takes a contour image drawn by the designers as input and then outputs the colorized icon image. Similar ideas have been adopted to colorize black-and-white Manga characters [5,8,14,42] and achieved great success. To control the colorization process, additional inputs, such as stroke colors and style images, are fed into the network as well.…”

Section: Introductionmentioning

confidence: 99%

Adversarial Colorization of Icons Based on Contour and Color Conditions

Sun

Lai

Wong

et al. 2019

Proceedings of the 27th ACM International Conference on Multimedia

View full text Add to dashboard Cite

We present a system to help designers create icons that are widely used in banners, signboards, billboards, homepages, and mobile apps. Designers are tasked with drawing contours, whereas our system colorizes contours in different styles. This goal is achieved by training a dual conditional generative adversarial network (GAN) on our collected icon dataset. One condition requires the generated image and the drawn contour to possess a similar contour, while the other anticipates the image and the referenced icon to be similar in color style. Accordingly, the generator takes a contour image and a man-made icon image to colorize the contour, and then the discriminators determine whether the result fulfills the two conditions. The trained network is able to colorize icons demanded by designers and greatly reduces their workload. For the evaluation, we compared our dual conditional GAN to several state-of-the-art techniques. Experiment results demonstrate that our network is over the previous networks. Finally, we will provide the source code, icon dataset, and trained network for public use. CCS CONCEPTS• Information systems → Multimedia content creation; • Humancentered computing → Interactive systems and tools.

show abstract

Editable Generative Adversarial Networks: Generating and Editing Faces Simultaneously

Baek

Bang

Shim

2019

Computer Vision – ACCV 2018

View full text Add to dashboard Cite

We propose a novel framework for simultaneously generating and manipulating the face images with desired attributes. While the state-of-the-art attribute editing technique has achieved the impressive performance for creating realistic attribute effects, they only address the image editing problem, using the input image as the condition of model. Recently, several studies attempt to tackle both novel face generation and attribute editing problem using a single solution. However, their image quality is still unsatisfactory. Our goal is to develop a single unified model that can simultaneously create and edit high quality face images with desired attributes. A key idea of our work is that we decompose the image into the latent and attribute vector in low dimensional representation, and then utilize the GAN framework for mapping the low dimensional representation to the image. In this way, we can address both the generation and editing problem by learning the generator. For qualitative and quantitative evaluations, the proposed algorithm outperforms recent algorithms addressing the same problem. Also, we show that our model can achieve the competitive performance with the state-of-the-art attribute editing technique in terms of attribute editing quality.

show abstract

Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN

Cited by 11 publications

References 7 publications

Twin-GAN -- Unpaired Cross-Domain Image Translation with Weight-Sharing GANs

Twin-GAN -- Unpaired Cross-Domain Image Translation with Weight-Sharing GANs

Adversarial Colorization of Icons Based on Contour and Color Conditions

Editable Generative Adversarial Networks: Generating and Editing Faces Simultaneously

Contact Info

Product

Resources

About